© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23668
    Prev
    Next
    INDEX
    Explanations

    Itanium, Veloster, Avensis, Santa Fe, Max

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dale
    -0.11
    管å±Ģ
    -0.10
    ç¢İçīĩ
    -0.10
    кал
    -0.09
    ç¼¢
    -0.09
    èĺĸ
    -0.09
    çĽijçĿ£ç®¡çIJĨ
    -0.09
    åĩºç§Ł
    -0.09
    iska
    -0.09
    avers
    -0.09
    POSITIVE LOGITS
    çļĦ缮åħī
    0.09
    озд
    0.08
    bung
    0.08
    对ä»ĸ们
    0.08
     Curry
    0.08
    çĤ¹å¤´
    0.08
     Mang
    0.08
    urry
    0.08
    oding
    0.08
    /entities
    0.08
    Activations Density 0.018%

    No Known Activations